CodeRankLLM
is a 7B LLM fine-tuned for listwise code-reranking. When combined with performant code retrievers like
CodeRankEmbed
, it significantly enhances the quality of retrieved results for various code retrieval tasks.
We release the scripts to evaluate our model's performance
here
.
Training
Our code reranker is based on LLM-based listwise reranking, which has gained prominence for the ability to score multiple passages simultaneously. Training data for listwise reranking was generated by selecting 50,000 <query, positive, negatives> tuples from our high-quality dataset
CoRNStack
, filtered to ensure higher similarity scores and better ranks for the positives. Since CoRNStack doesn't contain the ranked ordering data required for training listwise rerankers, we leverage
Qwen-2.5-32B-Instruct
LLM provided ranked orderings for each example to serve as ranking supervision. We initialize our reranker with
Qwen2.5-Coder-7B-Instruct
and fine-tune using a language modeling objective that minimizes the prediction error of the next token in the sequence.
Runs of nomic-ai CodeRankLLM on huggingface.co
81
Total runs
0
24-hour runs
-3
3-day runs
-5
7-day runs
-5
30-day runs
More Information About CodeRankLLM huggingface.co Model
CodeRankLLM huggingface.co is an AI model on huggingface.co that provides CodeRankLLM's model effect (), which can be used instantly with this nomic-ai CodeRankLLM model. huggingface.co supports a free trial of the CodeRankLLM model, and also provides paid use of the CodeRankLLM. Support call CodeRankLLM model through api, including Node.js, Python, http.
CodeRankLLM huggingface.co is an online trial and call api platform, which integrates CodeRankLLM's modeling effects, including api services, and provides a free online trial of CodeRankLLM, you can try CodeRankLLM online for free by clicking the link below.
nomic-ai CodeRankLLM online free url in huggingface.co:
CodeRankLLM is an open source model from GitHub that offers a free installation service, and any user can find CodeRankLLM on GitHub to install. At the same time, huggingface.co provides the effect of CodeRankLLM install, users can directly use CodeRankLLM installed effect in huggingface.co for debugging and trial. It also supports api for free installation.